SOTAVerified

Novel Concepts

Measures the ability of models to uncover an underlying concept that unites several ostensibly disparate entities, which hopefully would not co-occur frequently. This provides a limited test of a model's ability to creatively construct the necessary abstraction to make sense of a situation that it cannot have memorized in training.

Source: BIG-bench

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 121–130 of 158 papers

TitleStatusHype
Rockafellian Relaxation and Stochastic Optimization under Perturbations—0
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs—0
Benchmarking the human brain against computational architectures—0
Automating string processing in spreadsheets using input-output examples—0
Schema Independent Relational Learning—0
SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning—0
Sequential Local Learning for Latent Graphical Models—0
Zero-Shot Learning by Generating Pseudo Feature Representations—0
Situational Grounding within Multimodal Simulations—0
Weakly Supervised Open-Vocabulary Object Detection—0
Show:102550
← PrevPage 13 of 16Next →

No leaderboard results yet.